Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules


Sparse neural networks have various computational benefits while often being able to maintain or improve the generalization performance of their dense counterparts. Popular sparsification methods have focused on what to sparsify, i.e. which redundant components to remove from neural networks, while when to sparsify, has received less attention and is usually handled using heuristics or simple schedules. In this work, we focus on learning sparsity schedules from scratch using reinforcement learning. In simple CNNs and ResNet-18, we show that our learned schedules are diverse across layers and training steps, while achieving competitive performance when compared to naive handcrafted schedules. Our methodology is general-purpose and can be applied to learning effective sparsity schedules across any pruning implementation.

Workshop on Dynamic Neural Networks at ICML
Benjamin Rosman
Benjamin Rosman
Lab Director

I am a Professor in the School of Computer Science and Applied Mathematics at the University of the Witwatersrand in Johannesburg. I work in robotics, artificial intelligence, decision theory and machine learning.